Multi-robot teams plan smart sample collection and handoff paths
MA-LIPP: Cooperative Multi-Agent Load-Aware Informative Path Planning for Heterogeneous Robot Teams
Robotics
Summary
Collecting samples with a single robot is hard because it must carry everything back to a base, limiting where it can go. The authors study how teams of different robots can work together by passing samples between each other without meeting up at the same time. They created ways to plan these sample pickup and handoff routes that save energy and cover more ground. Their method is nearly as good as an exact solution and helps robots explore more efficiently than working one after another.
What this means in practice
- •For environmental monitoring teams: Coordinate teams of different robots to collect and transport samples efficiently without waiting for rendezvous, enabling more extensive environmental data gathering.
- •For disaster response units: Plan robot teams to gather hazardous samples with asynchronous handoffs, reducing energy use and increasing area coverage in complex disaster zones.
Authors
Hojune Kim, Guangyao Shi, Gaurav S. Sukhatme
Abstract
Field robotics missions often require physical samples to be returned to laboratories for analysis, making path planning inherently load-aware and order-dependent as accumulated samples increase payload and traversal energy costs. In single-robot Load-Aware Informative Path Planning (LIPP), this rigidly couples sensing with hauling: a solitary robot must transport every collected sample, forcing frequent depot returns that severely restrict its spatial coverage. Heterogeneous multi-robot teams can overcome this bottleneck by dividing labor---enabling high-precision samplers to collect while high-capacity carriers handle transport. However, this introduces a complex coordination challenge regarding when, where, what, and to whom handoffs should occur on top of the LIPP problem. To address this tightly coupled problem, we introduce Multi-Agent LIPP (MA-LIPP), which enables teams to cooperate through asynchronous "dead drops," allowing one robot to deposit samples for another to retrieve later without requiring synchronous rendezvous. We formulate MA-LIPP as an exact Mixed-Integer Quadratic Program (MIQP) alongside a scalable Pairwise Large-Neighborhood Search (LNS) heuristic for complex real-world applications. The heuristic matches exact optima in $95.5\%$ of certified cases and reduces weighted posterior variance by $16.1$--$19.8\%$ relative to a sequential baseline on larger instances of up to 12 robots, providing a robust framework for cooperative physical-sampling missions.